{"total":21,"rows":[{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","cited_by_count":94,"area":"safety"},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57,"area":"safety"},{"id":"2303.15180","title":"Detecting Backdoors in Pre-trained Encoders","created":"2023-03-23","cited_by_count":55,"area":"safety"},{"id":"2309.04777","title":"Towards Robust Model Watermark via Reducing Parametric Vulnerability","created":"2023-09-09","cited_by_count":10,"area":"safety"},{"id":"2507.05113","title":"CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation","created":"2025-07-07","cited_by_count":10,"area":"safety"},{"id":"2210.06894","title":"Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation","created":"2022-10-13","cited_by_count":8,"area":"safety"},{"id":"2305.04547","title":"Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias","created":"2023-05-08","cited_by_count":8,"area":"safety"},{"id":"2406.03508","title":"Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders","created":"2024-06-05","cited_by_count":8,"area":"safety"},{"id":"2511.07210","title":"Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization","created":"2025-11-10","cited_by_count":7,"area":"safety"},{"id":"2404.11265","title":"The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data","created":"2024-04-17","cited_by_count":4,"area":"safety"},{"id":"2406.02619","title":"Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits","created":"2024-06-03","cited_by_count":4,"area":"safety"},{"id":"2505.10859","title":"Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning","created":"2025-05-16","cited_by_count":4,"area":"safety"},{"id":"2409.01185","title":"Backdoor Defense through Self-Supervised and Generative Learning","created":"2024-09-02","cited_by_count":2,"area":"safety"},{"id":"2109.04566","title":"SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural Networks","created":"2021-09-09","cited_by_count":1,"area":"safety"},{"id":"2504.06407","title":"Understanding Machine Unlearning Through the Lens of Mode Connectivity","created":"2025-04-08","cited_by_count":1,"area":"safety"},{"id":"2211.01808","title":"Dormant Neural Trojans","created":"2022-11-02","cited_by_count":0,"area":"safety"},{"id":"2506.15112","title":"PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning","created":"2025-06-18","cited_by_count":0,"area":"safety"},{"id":"2507.19905","title":"ConSeg: Contextual Backdoor Attack Against Semantic Segmentation","created":"2025-07-26","cited_by_count":0,"area":"safety"},{"id":"2602.03316","title":"Invisible Clean-Label Backdoor Attacks for Generative Data Augmentation","created":"2026-02-03","cited_by_count":0,"area":"safety"},{"id":"2605.22871","title":"Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity","created":"2026-05-20","cited_by_count":0,"area":"safety"},{"id":"2607.23970","title":"Understanding Machine Unlearning Through the Lens of Mode Connectivity","created":"2026-07-27","cited_by_count":0,"area":"safety"}],"next_cursor":null}